Leverage Perplexity AI's robust knowledge base for accurate, current answers to your questions. This agent combines advanced language models with real-time information to provide comprehensive responses with relevant citations.
Playground
Your organization, project and token stay in this browser's local storage and are sent
straight to the API — this page never sees them.
POST
item
question
requiredThe question you want to ask Perplexity
config
model
Perplexity model to use
temperature
Temperature for the Perplexity model
Billing
Fixed cost per question asked, plus one AI web search for every search the model runs -- it may run more than one for a broad question -- and the model usage for the answer. Selecting a more capable model raises the per-token rates severalfold; an unrecognised model name is not billed for tokens at all.
These usage SKUs can be charged on a call.
SKU
Credits
Description
Tool call
1 per request
Charged once per successful item, on top of any usage below.
AI web search
5 per query
A model answering from live web results it retrieved itself. The retrieval is billed on top of the model's own usage.
Sonar (standard), input
1,000 per million tokens
Tokens the model reads from the prompt you send.
Sonar (standard), output
1,000 per million tokens
Tokens the model writes in its answer.
Sonar (standard), read from cache
1,000 per million tokens
Tokens the model reads from a cached prompt. Cheaper than a fresh read.
Sonar Pro (standard), input
3,000 per million tokens
Tokens the model reads from the prompt you send.
Sonar Pro (standard), output
15,000 per million tokens
Tokens the model writes in its answer.
Sonar Pro (standard), read from cache
3,000 per million tokens
Tokens the model reads from a cached prompt. Cheaper than a fresh read.
Schemas
item is what you send, config how the tool behaves,
and the response is what you get back.
Item
object
Properties
questionstringrequired
The question you want to ask Perplexity
min length 1
Example
{
"question": "string"
}
Configuration
object
Properties
modelstring
Perplexity model to use
Default: "sonar"
temperaturenumber
Temperature for the Perplexity model
Default: 0.3
min 0.0, max 2.0
Example
{
"model": "sonar",
"temperature": 0.3
}
Response
object
Properties
answerstringrequired
The answer from Perplexity
citationsarrayrequired
List of citation URLs
search_resultsarrayrequired
List of search results used to generate the answer